Leveraging Knowledge Graphs to Enhance Fault Detection in Facility Management

Abstract

Digital twins are the most commonly used tool for improving efficiency in facilities management. However, existing digital twins lack semantics, leaving the facility maintenance team responsible for interpreting and responding to faults. To enable semantics in a digital twin, it must rely not only on the data produced by sensors, but also on a deeper knowledge of the system and the processes taking place within it. The paper proposes a framework for the automated generation of Bayesian Networks (BNs) from a single data source - a knowledge graph - which should store information from different sources, such as topology, documents originally written in natural language, and domain-specific ontologies based on RDF (Resource Description Framework). BNs will be used to infer failure symptoms and causes, while automated BN generation is expected to solve a scalability problem. These coupled tools will be investigated in terms of supporting the facility manager in decision making.